英语翻译利用数据预处理方法,剔除无关属性、获得相应的特征子集,这些不同的特征子集中的样本往往具有相似的模式,在不同的特征子集上进行规则挖掘可大大提高关联规则挖掘的效率和有

英语翻译利用数据预处理方法,剔除无关属性、获得相应的特征子集,这些不同的特征子集中的样本往往具有相似的模式,在不同的特征子集上进行规则挖掘可大大提高关联规则挖掘的效率和有
英语翻译
利用数据预处理方法,剔除无关属性、获得相应的特征子集,这些不同的特征子集中的样本往往具有相似的模式,在不同的特征子集上进行规则挖掘可大大提高关联规则挖掘的效率和有效性.本文分析基于关系代数的关联规则挖掘算法,把得到的特征子集利用关系矩阵及相关运算挖掘出频繁项集,该算法只需扫描数据库一次,减少了时间开销.挖掘出频繁项集后,生成得到最大频繁项集和频繁闭项集,解决了产生大量冗余规则的问题.通过对算法性能分析比较,基于关系代数的关联规则挖掘算法优于经典的Apriori算法,并在机器学习公用数据集上进行验证,在不同的数据样本量、不同的支持度下,通过仿真实验比较了这两个算法的执行时间,验证了基于关系代数的关联规则挖掘算法的优化效果.在教学评价数据集上挖掘最大频繁项集和频繁闭项集,实验结果证明基于关系代数的关联规则挖掘算法优于Apriori算法,使用频繁闭项集产生关联规则解决了冗余规则问题.

英语翻译利用数据预处理方法,剔除无关属性、获得相应的特征子集,这些不同的特征子集中的样本往往具有相似的模式,在不同的特征子集上进行规则挖掘可大大提高关联规则挖掘的效率和有
Use data pretreatment methods and eliminate the irrelevant attributes and the corresponding feature subsets, these different feature subset of sample often similar pattern, in different feature subsets on rule mining association rules mining can greatly improve the efficiency and effectiveness. In this paper based on the relational algebra association rule mining algorithm, the feature subsets and related operations using relation matrix unearths the frequent itemsets, this algorithm only requires scanning databases, reduce time once overhead. Dig out frequent itemsets, generate maximum frequent itemsets and frequent closed itemsets produced, solve the problem of redundant rules. Through analysis and comparison of the algorithm, based on the performance of the relational algebra association rule mining algorithm is superior to classical Apriori algorithm, and in the public data sets of machine learning, in different data sample, different support, through the simulation experiment comparison between the two algorithm's execution time based on the relational algebra, verify the algorithm for mining association rules optimization effect. In the teaching evaluation data sets on mining maximum frequent itemsets and frequent closed itemsets based on the experimental results prove that the relational algebra algorithm for mining association rules algorithm, using Apriori superior frequent closed itemsets produces association rules redundancy rules solved the problem.